[pymvpa] mapper.reverse1
Florian Baumgartner
florian.baumgartner at ovgu.de
Mon Mar 29 15:36:05 UTC 2010
Hi all,
I currently try to adapt my old PyMVPA scripts to the new snapshot
version. Using the a Event-Related Mapper on fMRI-data I am getting a
memory error when I try to remap a data vector back in the original
space. Converting all samples of the dataset back works fine. Do you
have any suggestion for the solution?
Thanks
Florian
>> ds = fmri_dataset(fmri_src,mask=brainmask_src)
>> evds = eventrelated_dataset(ds, events=evs)
>> poly_detrend(evds, polyord=1,
>> chunks_attr='chunks'
>> #,opt_regs=McFlirtParams(mcpar_src) <-- how is that
>> working by the way
)
>> zscore(evds, chunks_attr='chunks')
>>evds.mapper
ChainMapper(mappers=[FlattenMapper(shape=(25, 160, 160),
inspace='voxel_indices'), FeatureSliceMapper(slicearg=array([False,
False, False, ..., False, False, False], dtype=bool), dshape=(640000,),
inspace=None), BoxcarMapper(boxlength=3, offset=0, startpoints=[ 8
20 24 26 30 44 63 64 68 72 81 90 108 116 124 127 129 138 142
164 176 183 187 190 214 232 243 251 263 265 271 274 276 282 290 295 306
316 330 346 356 358 361 363 375 378 392 395 406 413 434 438 441 445 457
467 478 481 487 495 517 519 531 539 552 559 565 568 577 584 586 589 608
617 620 622 632 645 653 655 662 666 675 677 710 720 722 747 750 752 756
767 777 783 785 791], inspace='event'), FlattenMapper(shape=(3,
115211), inspace=None), PolyDetrendMapper(polyord=1,
chunks_attr='chunks', opt_regs=None, inspace=None),
ZScoreMapper(inspace=None)], inspace=None)
>>evds.shape
(96, 345633)
>>evds.mapper.reverse1(zeros(evds.shape[1]))
---------------------------------------------------------------------------
MemoryError Traceback (most recent call
last)
/media/data/feanor/baumgartner/binding/master2.py in <module>()
----> 1
2
3
4
5
/usr/lib/pymodules/python2.5/mvpa/mappers/base.pyc in reverse1(self,
data) 751 "Reversing single %s-shaped input
though '%s'." 752 % (mp.shape, str(m)))
--> 753 mp = m.reverse1(mp)
754 except NotImplementedError:
755 if __debug__:
/usr/lib/pymodules/python2.5/mvpa/mappers/base.pyc in reverse1(self,
data) 262 """
263 if isinstance(data, np.ndarray):
--> 264 return self.reverse(data[np.newaxis])[0]
265 else:
266 return self.reverse(np.array([data]))[0]
/usr/lib/pymodules/python2.5/mvpa/mappers/base.pyc in reverse(self,
data) 251 return self._reverse_dataset(data)
252 else:
--> 253 return self._reverse_data(data)
254
255
/usr/lib/pymodules/python2.5/mvpa/mappers/base.pyc in
_reverse_data(self, data) 376 # features
377 mapped.resize(data.shape[:1] + self.__dshape +
data.shape[2:], --> 378 refcheck=False)
379 mapped.fill(0)
380 mapped[:, self._slicearg] = data
MemoryError: cannot allocate memory for array
>>evds.mapper.reverse(zeros(evds.shape))
works fine
>> wtf()
Current date: 2010-03-29 18:26
PyMVPA:
Version: 0.5.0.dev+783+gde39
Path: /usr/lib/pymodules/python2.5/mvpa/__init__.pyc
Version control (GIT):
GIT information could not be obtained due
"/usr/lib/pymodules/python2.5/mvpa/.. is not under GIT"
SYSTEM: OS: posix Linux 2.6.32-trunk-amd64 #1 SMP Sun Jan 10
22:40:40 UTC 2010 Distribution:
debian/squeeze/sid
EXTERNALS: Present: atlas_fsl, cPickle, ctypes, good
scipy.stats.rv_discrete.ppf, griddata, gzip, libsvm, libsvm verbosity
control, lxml, matplotlib, mdp, mdp ge 2.4, nifti, nifti ge
0.20090205.1, numpy, pylab, pylab plottable, pywt, pywt wp reconstruct,
reportlab, running ipython env, scipy, sg ge 0.6.4, sg ge 0.6.5,
sg_fixedcachesize, shogun, shogun.krr, shogun.mpd Absent:
atlas_pymvpa, elasticnet, glmnet, good scipy.stats.rdist, h5py,
hcluster, lars, nipy, nose, openopt, pprocess, pywt wp reconstruct
fixed, rpy, rpy2, shogun.lightsvm, shogun.svrlight, weave Versions of
critical externals: shogun:full : 0.9.1_r4481_2009-11-16_10:14_
shogun:rev : 4481 reportlab : 2.4 shogun : 0.9.1 scipy :
0.7.0 ipython : 0.10 mdp : 2.5 numpy : 1.3.0
ctypes : 1.0.3 matplotlib :
0.99.1.1 lxml :
2.2.6 nifti :
0.20090303.1 numpy :
1.3.0 pywt :
0.1.7 shogun :
v0.9.1_r4481_2009-11-16_10:14_ Matplotlib backend:
TkAgg
RUNTIME: PyMVPA Environment
Variables: PyMVPA Runtime
Configuration:
[externals] have griddata =
yes have pprocess =
no have atlas_pymvpa =
no have good scipy.stats.rdist =
no have pylab plottable =
yes have pywt wp reconstruct =
yes have ctypes =
yes have lxml =
yes have running ipython env =
yes have sg_fixedcachesize =
yes have elasticnet =
no have shogun.mpd =
yes have matplotlib =
yes have pywt wp reconstruct fixed =
no have scipy =
yes have reportlab =
yes have openopt =
no have libsvm =
yes have nifti ge 0.20090205.1 =
yes have nose =
no have weave =
no have atlas_fsl =
yes have h5py =
no have hcluster =
no have sg ge 0.6.4 =
yes have sg ge 0.6.5 =
yes have good scipy.stats.rv_discrete.ppf =
yes have libsvm verbosity control =
yes have mdp ge 2.4 =
yes have shogun.svrlight =
no have rpy =
no have lars =
no have nipy =
no have glmnet = no
have shogun = yes
have nifti = yes
have shogun.krr = yes
have cpickle = yes
have mdp = yes
have numpy = yes
have pylab = yes
have rpy2 = no
have shogun.lightsvm = no
have pywt = yes
have gzip = yes
[general]
verbose = 1
Process Information:
Name: ipython
State: R (running)
Tgid: 14328
Pid: 14328
PPid: 14310
TracerPid: 0
Uid: 1021 1021 1021 1021
Gid: 100 100 100 100
FDSize: 256
Groups: 24 29 33 44 46 100 105 1001 1003
VmPeak: 2867388 kB
VmSize: 2360292 kB
VmLck: 0 kB
VmHWM: 2414668 kB
VmRSS: 1898968 kB
VmData: 1954300 kB
VmStk: 264 kB
VmExe: 1148 kB
VmLib: 67648 kB
VmPTE: 4476 kB
Threads: 2
SigQ: 0/16382
SigPnd: 0000000000000000
ShdPnd: 0000000000000000
SigBlk: 0000000000000000
SigIgn: 0000000001001000
SigCgt: 0000000180000002
CapInh: 0000000000000000
CapPrm: 0000000000000000
CapEff: 0000000000000000
CapBnd: ffffffffffffffff
Cpus_allowed: ffff
Cpus_allowed_list: 0-15
Mems_allowed: 00000000,00000001
Mems_allowed_list: 0
voluntary_ctxt_switches: 4242
nonvoluntary_ctxt_switches: 3961
Stack usage: 260 kB
More information about the Pkg-ExpPsy-PyMVPA
mailing list